{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:ATBZ64PVUN5CHURINIRISM7JSZ","short_pith_number":"pith:ATBZ64PV","schema_version":"1.0","canonical_sha256":"04c39f71f5a37a23d2286a228933e9964d745af4ccd92dc252139ed3159647a0","source":{"kind":"arxiv","id":"2006.12463","version":3},"attestation_state":"computed","paper":{"title":"Slimming Neural Networks using Adaptive Connectivity Scores","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.IT","cs.LG","math.IT"],"primary_cat":"cs.CV","authors_text":"Dawsin Blanchard, Jason J. Corso, Madan Ravi Ganesh, Salimeh Yasaei Sekeh","submitted_at":"2020-06-22T17:45:16Z","abstract_excerpt":"In general, deep neural network (DNN) pruning methods fall into two categories: 1) Weight-based deterministic constraints, and 2) Probabilistic frameworks. While each approach has its merits and limitations there are a set of common practical issues such as, trial-and-error to analyze sensitivity and hyper-parameters to prune DNNs, which plague them both. In this work, we propose a new single-shot, fully automated pruning algorithm called Slimming Neural networks using Adaptive Connectivity Scores (SNACS). Our proposed approach combines a probabilistic pruning framework with constraints on the"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2006.12463","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2020-06-22T17:45:16Z","cross_cats_sorted":["cs.IT","cs.LG","math.IT"],"title_canon_sha256":"348acd58ea2338b3e6c3d6ba43221c5f16a820280ccb3b265b2913d183f48f7e","abstract_canon_sha256":"b958f1431733db43326d98f2cd94d692d88e0faed73541f953827d8693cf537c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:41:49.534000Z","signature_b64":"UxWlNyyUqfS5IN8wEtc5CvT52rVbtezAqgskL1U7nsW5c93TOy9Pvp7wjgKoir4H8MklBAQcIFHjX/tK5P+VCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"04c39f71f5a37a23d2286a228933e9964d745af4ccd92dc252139ed3159647a0","last_reissued_at":"2026-07-05T03:41:49.533653Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:41:49.533653Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Slimming Neural Networks using Adaptive Connectivity Scores","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.IT","cs.LG","math.IT"],"primary_cat":"cs.CV","authors_text":"Dawsin Blanchard, Jason J. Corso, Madan Ravi Ganesh, Salimeh Yasaei Sekeh","submitted_at":"2020-06-22T17:45:16Z","abstract_excerpt":"In general, deep neural network (DNN) pruning methods fall into two categories: 1) Weight-based deterministic constraints, and 2) Probabilistic frameworks. While each approach has its merits and limitations there are a set of common practical issues such as, trial-and-error to analyze sensitivity and hyper-parameters to prune DNNs, which plague them both. In this work, we propose a new single-shot, fully automated pruning algorithm called Slimming Neural networks using Adaptive Connectivity Scores (SNACS). Our proposed approach combines a probabilistic pruning framework with constraints on the"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2006.12463","kind":"arxiv","version":3},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2006.12463/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2006.12463","created_at":"2026-07-05T03:41:49.533710+00:00"},{"alias_kind":"arxiv_version","alias_value":"2006.12463v3","created_at":"2026-07-05T03:41:49.533710+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2006.12463","created_at":"2026-07-05T03:41:49.533710+00:00"},{"alias_kind":"pith_short_12","alias_value":"ATBZ64PVUN5C","created_at":"2026-07-05T03:41:49.533710+00:00"},{"alias_kind":"pith_short_16","alias_value":"ATBZ64PVUN5CHURI","created_at":"2026-07-05T03:41:49.533710+00:00"},{"alias_kind":"pith_short_8","alias_value":"ATBZ64PV","created_at":"2026-07-05T03:41:49.533710+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2501.15592","citing_title":"Information Consistent Pruning: How to Efficiently Search for Sparse Networks?","ref_index":12,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ATBZ64PVUN5CHURINIRISM7JSZ","json":"https://pith.science/pith/ATBZ64PVUN5CHURINIRISM7JSZ.json","graph_json":"https://pith.science/api/pith-number/ATBZ64PVUN5CHURINIRISM7JSZ/graph.json","events_json":"https://pith.science/api/pith-number/ATBZ64PVUN5CHURINIRISM7JSZ/events.json","paper":"https://pith.science/paper/ATBZ64PV"},"agent_actions":{"view_html":"https://pith.science/pith/ATBZ64PVUN5CHURINIRISM7JSZ","download_json":"https://pith.science/pith/ATBZ64PVUN5CHURINIRISM7JSZ.json","view_paper":"https://pith.science/paper/ATBZ64PV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2006.12463&json=true","fetch_graph":"https://pith.science/api/pith-number/ATBZ64PVUN5CHURINIRISM7JSZ/graph.json","fetch_events":"https://pith.science/api/pith-number/ATBZ64PVUN5CHURINIRISM7JSZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ATBZ64PVUN5CHURINIRISM7JSZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ATBZ64PVUN5CHURINIRISM7JSZ/action/storage_attestation","attest_author":"https://pith.science/pith/ATBZ64PVUN5CHURINIRISM7JSZ/action/author_attestation","sign_citation":"https://pith.science/pith/ATBZ64PVUN5CHURINIRISM7JSZ/action/citation_signature","submit_replication":"https://pith.science/pith/ATBZ64PVUN5CHURINIRISM7JSZ/action/replication_record"}},"created_at":"2026-07-05T03:41:49.533710+00:00","updated_at":"2026-07-05T03:41:49.533710+00:00"}